Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
from extract import take_webdata
|
| 3 |
+
from PIL import Image
|
| 4 |
+
from io import BytesIO
|
| 5 |
+
|
| 6 |
+
def main():
|
| 7 |
+
st.title("Website Content Exctractor")
|
| 8 |
+
|
| 9 |
+
# Get website URL from user input
|
| 10 |
+
url = st.text_input("Enter a URL:", "")
|
| 11 |
+
if st.button("Proceed"):
|
| 12 |
+
if not url:
|
| 13 |
+
st.warning("URL is empty.")
|
| 14 |
+
else:
|
| 15 |
+
visualize(url)
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
def visualize(url):
|
| 19 |
+
try:
|
| 20 |
+
# Fetch and display the website content
|
| 21 |
+
with st.spinner("loading website data ..."):
|
| 22 |
+
# innerHTML = get_innerHTML(url)
|
| 23 |
+
html_image, html_content = take_webdata(url)
|
| 24 |
+
st.subheader("Website title:")
|
| 25 |
+
if html_content:
|
| 26 |
+
st.info(html_content)
|
| 27 |
+
else:
|
| 28 |
+
st.error("Error: empty html content")
|
| 29 |
+
st.subheader("Website preview:")
|
| 30 |
+
if html_image:
|
| 31 |
+
st.image(html_image)
|
| 32 |
+
else:
|
| 33 |
+
st.error("Error: empty html preview")
|
| 34 |
+
|
| 35 |
+
|
| 36 |
+
except Exception as e:
|
| 37 |
+
st.error(f"Error: {e}")
|
| 38 |
+
|
| 39 |
+
|
| 40 |
+
|
| 41 |
+
if __name__ == "__main__":
|
| 42 |
+
main()
|